Skip to content

fix(compiler): parse named HTML entities containing digits #67229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
yogeshwaran-c wants to merge 1 commit into
base: main
Choose a base branch
from
+38 −1
Open

fix(compiler): parse named HTML entities containing digits #67229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion packages/compiler/src/ml_parser/lexer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1431,7 +1431,12 @@ function isDigitEntityEnd(code: number): boolean {
}

function isNamedEntityEnd(code: number): boolean {
return code === chars.$SEMICOLON || code === chars.$EOF || !chars.isAsciiLetter(code);
// Named entities may contain digits (e.g. ¹, ½, ▓).
return (
code === chars.$SEMICOLON ||
code === chars.$EOF ||
!(chars.isAsciiLetter(code) || chars.isDigit(code))
);
}

function isExpansionCaseStart(peek: number): boolean {
Expand Down
11 changes: 11 additions & 0 deletions packages/compiler/test/ml_parser/html_parser_spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,17 @@ describe('HtmlParser', () => {
]);
});

it('should parse named HTML entities containing digits', () => {
expect(humanizeDom(parser.parse('<div>&sup1;</div>', 'TestComp'))).toEqual([
[html.Element, 'div', 0],
[html.Text, '\u00B9', 1, [''], ['\u00B9', '&sup1;'], ['']],
]);
expect(humanizeDom(parser.parse('<div>&frac12;</div>', 'TestComp'))).toEqual([
[html.Element, 'div', 0],
[html.Text, '\u00BD', 1, [''], ['\u00BD', '&frac12;'], ['']],
]);
});

it('should normalize line endings within CDATA', () => {
const parsed = parser.parse('<![CDATA[ line 1 \r\n line 2 ]]>', 'TestComp');
expect(humanizeDom(parsed)).toEqual([
Expand Down
21 changes: 21 additions & 0 deletions packages/compiler/test/ml_parser/lexer_spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2094,6 +2094,27 @@ describe('HtmlLexer', () => {
]);
});

it('should parse named entities containing digits', () => {
expect(tokenizeAndHumanizeParts('&sup1;')).toEqual([
[TokenType.TEXT, ''],
[TokenType.ENCODED_ENTITY, '\u00B9', '&sup1;'],
[TokenType.TEXT, ''],
[TokenType.EOF],
]);
expect(tokenizeAndHumanizeParts('&frac12;')).toEqual([
[TokenType.TEXT, ''],
[TokenType.ENCODED_ENTITY, '\u00BD', '&frac12;'],
[TokenType.TEXT, ''],
[TokenType.EOF],
]);
expect(tokenizeAndHumanizeParts('&blk34;')).toEqual([
[TokenType.TEXT, ''],
[TokenType.ENCODED_ENTITY, '\u2593', '&blk34;'],
[TokenType.TEXT, ''],
[TokenType.EOF],
]);
});

it('should parse hexadecimal entities', () => {
expect(tokenizeAndHumanizeParts('&#x41;&#X41;')).toEqual([
[TokenType.TEXT, ''],
Expand Down